• Date: November 16, 2009
  
• Time: 10:30a.m.
  
• Location: MI 03.07.023

Title: Model-Based Hand tracking from Monocular Video

Abstract:

I will present a model-based approach to 3D hand tracking from monocular video. The 3D hand pose, the hand texture and the illuminant are dynamically estimated through minimization of an objective function. Derived from an inverse problem formulation, the objective function enables explicit use of texture temporal continuity and shading information, while handling important self-occlusions and time-varying illumination. The minimization is done efficiently using a quasi-Newton method, for which we propose a rigorous derivation of the objective function gradient. Particular attention is given to terms related to the change of visibility near self-occlusion boundaries that are neglected in existing formulations. Toward this end we introduce new occlusion forces and show that using all gradient terms greatly improves the performance of the method.

Bio:

Martin de La Gorce obtained engineer diploma from ISEP in 2004 and a master in Vision and statistical learning in 2005 from Ecole Normale Supérieure de Cachan. He will defend in December his PhD^? on monocular hand tracking he conducted under the supervision of Nikos Paragios in the MAS Laboratory at Ecole Centrale de Paris. You can access to his publications here: http://www.mas.ecp.fr/vision/Personnel/martin/